Pitching is the starting point of an event in baseball games. Hence, locating pitching shots is a critical step in content analysis of a baseball game video. However, pitching frames vary with innings and games. Existing methods that require a great deal of effort to construct empirical rules or label training data do not capture the characteristics of various pitching frames very well. In this paper, we present an unsupervised method for pitching frame detection by using Markov random walk. A video stream is first divided into content-homogeneous shots, and these shots are merged into states through hierarchical agglomerative clustering. Then, the state with the highest visit probability according to the Markov random walk theory is deemed the set of pitching frames. Finally, a model trained on the pitching frames in the pitching state is further used to detect the remaining potential pitching frames in other states. Our experiments demonstrate that the proposed method yields satisfactory results in a variety of MLB games.

Camera control plays an important role in computer graphics for producing expressive images or animations. An appropriate viewing setting usually enhances the richness and quality of the generated results. In this paper, we propose an automatic method to determine the viewing parameters (e.g., camera position, camera distance) of motions based on the cinematography, artistic composition, and film editing rules. Our method addresses four main issues embedded in this problem: camera placement, shot determination, view selection of shot, and view refinement. For the first issue, based on cinematographic rules, we argue that character's vision and orientation as features, which are used to determine the number of cameras and their positions. For the second issue, we propose a motion segmentation method to convert a sequence into motion cuts, which represent the shots of the motion. For the third issue, a view selection algorithm based on visibility measure is devised to select an appropriate camera (view). For the fourth issue, we finalize the camera parameters by considering type of shot, common visual axis, and artistic composition. Comparing to fixed-view shots, our results convey more information by providing viewers with better visual appeal and scene understanding.

Abstract This paper presents a dynamics‐basedEffortsimulator so that a given motion can be modified according to specifiedEffortqualities. The basic idea of our approach is to establish relations betweenEffortfactors such as Space, Weight, Time, and Flow, and their corresponding dynamics parameters such as force, stiffness, inertia, damping, gravity, and etc in the simulator. Then, a motion with specifiedEffortquality can be realized by mapping it to appropriate dynamics parameters of the simulator. The proposed simulator has two merits: it is motion capture‐driven, therefore it is able to synthesize motion details and easily to be incorporated into popular motion capture applications. Besides, it is dynamics based and therefore it provides high‐level control intuition of motion dynamics in specifyingEffortqualities. To demonstrate the effectiveness of the proposed simulator, several experimental examples are presented and their results are discussed. Copyright © 2006 John Wiley & Sons, Ltd.

The study shows a human motion retrieval system, HUMOR. The system provides high-level multi-modal query interfaces so that users can choose a convenient modality, including text, stickman, images, and motion clip, to specify their queries. Besides, we propose a novel search method based on a well-structured index mechanism to retrieve human motion efficiently. The usability of the multi-modal user interface and the effectiveness of the proposed system has been demonstrated.

Abstract Human spontaneous motions such as walking and runing are seldom described in detail. However, some well designed motions such as conditioning and rehabilitation exercises are usually described in detail and edited into exercise manuals for training purpose. This paper presents a novel framework for synthesizing new motions based on given motion manuals and corresponding motion capture examples. First, using text analysis method, a set of basic motion texts is extracted from exercise manuals and converted into text normal form. Then we introduce an annotation method to build the mapping table between basic motion texts and their corresponding motion clips in the given examples. To facilitate the search for proper motion clips, a multi‐dimensional index structure based on posture parameters is proposed. Then a new motion with given textual description can be synthesized by converting the description sentences into a sequence of text normal forms and then concatenating the corresponding motion clips to form the desired motion. Moreover, to realize the smooth concatenation, we show that it can be achieved by finding an appropriate path in the proposed multi‐dimensional index space. Several experimental examples are given to demonstrate the proposed method is effective in synthesizing desired motions according to given descriptions. Copyright © 2004 John Wiley & Sons, Ltd.

A fuzzy logic framework is proposed to alleviate two problems in traditional CBIR systems, including the semantic gap and the perception subjectivity. The proposed framework consists of two major parts, including (1) model construction and (2) query comparison. In the model construction part, fuzzy linguistic terms with associated fuzzy membership functions are automatically generated through an unsupervised fuzzy clustering algorithm. The linguistic terms provide a nature way of expressing user's concepts, and the membership functions characterize the mapping between image features and human visual concepts. We also define the syntax and semantics rules of a query description language to unify the query expression of textual descriptions, visual examples, and relevance feedbacks. In the query comparison part, a similarity function is inferred based on user's feedbacks to measure the similarity between the query and each image in the database. The user's preference is also captured and retained in his/her own profile to achieve personalization. Our work provides a unified and comprehensive framework for incorporation a fuzzy approach into CBIR systems. To verify our CBIR framework, we select Tamura features to describe and retrieve texture images. Experimental results show that the proposed framework is indeed effective to alleviate the semantic gap and the perception subjectivity problems.

In this study, we propose a simple and effective approach to synthesize new motions from a given sequence of continuous motion capture data. First an index function, based on posture features of each motion frame, is introduced to segment the given motion capture data into indexed motion clips. Then based on the fact that motion coherence implies index coherence, a new motion with start frame f/sub start/ and end frame fend can be synthesized by finding a smooth path connecting f/sub start/ to f/sub end/ in the multidimensional index space. Moreover, an algorithm for finding smooth paths is presented and a relevance feedback mechanism is provided to refine the results. The merit of the proposed framework is that it can generate fast prototyping of desired motions with only a small amount of preprocessing time. Experimental results are given to shown the effectiveness of the proposed framework.

In this study, we propose a fuzzy logic CBIR system for textures, named LinStar Texture (i.e., Linguistic Star for Textures). The proposed system consists of two major phases, including database creation and query comparison. In the database creation phase, six Tamura features are extracted to describe each texture image in the database. A term set on each Tamura feature is generated through a fuzzy clustering algorithm so that degrees of appearance for the feature can be interpreted as five linguistic terms. In the query comparison phase, a user can pose textual descriptions or visual examples to find the desired textures. Furthermore, the query can be expressed as a logic composition of linguistic terms or Tamura feature values. The final similarity is then computed by aggregating each individual similarity through min-max composition rules. Experimental results reveal the proposed system is indeed effective. The retrieved images are perceptually satisfactory. The retrieval time is very fast.

In this correspondence, a new approach to retrieving images from a color image database is proposed. Each image in the database is represented by a two-dimensional pseudo-hidden Markov model (2-D PHMM), which characterizes the chromatic and spatial information about the image. In addition, a flexible pictorial querying method is used, by which users can paint the rough content of the desired images in a query picture. Image matching is achieved by comparing the query picture with each 2-D PHMM in the database. Experimental results show that the proposed approach is indeed effective.

A new approach to retrieving images from a color image database is proposed in this paper. Each image in the database is represented by a pseudo two-dimensional hidden Markov model (2D PHMM), where both the chromatic and spatial information about the image could be adequately involved. In addition, a pictorial querying method is used, by which the users can paint only rough contents of the desired images if their information concerning the desired images is not crisp. The use of the flexible querying mechanism and 2D PHMMs eliminates the drawbacks of utilizing textual descriptions to retrieve images. Furthermore, effective statistical matching between the query picture and each image in the database can be achieved. The probability of the query picture generated by each 2D PHMM is just considered as the matching score between the query and the corresponding image. The images which best satisfy the query can thus be retrieved. Promising experimental results show the feasibility and effectiveness of the proposed approach.

Abstract Let R = (V, E) be a unidirectional ring network where V corresponds to the set of nodes and E corresponds to the set of directed communication links. A partition of R divides R into several disjoint chains. For each partition P, there is associated a communication cost C(P). The optimal ring partition problem is to find a partition P* of R such that C(P*) = minpC(P). In this paper, we first formulate the ring partition problem into a recurrence relation. By solving the recurrence relation, we show that the ring partition can be accomplished distributively in one pass, i.e., the message complexity of our distributed ring partition algorithm is O(|V|), which is optimal. © 1993 by John Wiley & Sons, Inc.

The authors propose a new algorithm for finding the three-dimensional border of linear octrees stored in a one dimensional array. A simple method is proposed to check whether an octant is a border octant. Then, the border finding procedure can be carried out node by node according to their location code ordering. In order to improve the performance of the algorithm, a new and efficient neighbor finding technique is proposed. The time complexity of the proposed neighbor finding method is analyzed and proved to be O(1) on the average. Compared with the existing border algorithms, the proposed algorithm has the following advantages: (1) no preprocessing is required to arrange the input data according to their grouping factors, (2) the border found is already a sorted sequence of border voxels with no extra sorting required, and (3) the average time complexity is improved from O(N log N) to O(N), where N is the number of nodes in the linear octree.>